booking-mcp
Enables managing restaurant reservations over Streamable HTTP, with tools for booking, checking availability, cancelling, resources for reservation data, and prompts for drafting confirmations.
README

š½ļø booking-mcp
booking-mcp is a Model Context Protocol server for managing restaurant reservations, served over Streamable HTTP. It exposes tools to book a table, check availability, and cancel a reservation; resources to read the reservation book; and a prompt for drafting confirmations. When booking, the server gathers the guest's contact details from the user through elicitation.
š Requirements
- Python 3.13
- uv
š Usage
š¦ Setup
Create the virtual environment, install the SDK (mcp[cli,rich]) and dependencies, and install the package in editable mode:
uv sync
š„ļø Server
Start the server, which serves Streamable HTTP at http://127.0.0.1:8000/mcp:
uv run booking-mcp
š¶ Walkthrough
A standalone interactive client that runs in process, so nothing else needs to be running. It gives you a menu of actions and lets you answer the elicitation prompts yourself.
uv run python scripts/walkthrough.py
[!TIP]
Reservations persist to
var/bookings.jsonby default. SetBOOKING_DB_PATHto store them elsewhere:BOOKING_DB_PATH=/tmp/demo.json uv run python scripts/walkthrough.py
š§© MCP Surface
| Kind | Name | Notes |
|---|---|---|
| Tool | book_table(date, time, party_size) |
elicits name, phone, and notes from the user |
| Tool | cancel_booking(id) |
marks a reservation cancelled |
| Tool | check_availability(date, time) |
remaining tables for a slot |
| Resource | bookings://all |
every reservation, as JSON |
| Resource | bookings://{id} |
one reservation, as JSON |
| Resource | availability://{date} |
capacity for each slot on a date, as JSON |
| Prompt | confirmation_message(id) |
drafts a guest confirmation message |
š Layout
booking-mcp/
āāā src/booking_mcp/
ā āāā app.py # the shared MCPServer instance
ā āāā config.py # storage path + capacity limits
ā āāā models.py # Reservation domain model
ā āāā store.py # JSON file repository
ā āāā server.py # entrypoint: registers features, runs the server
ā āāā features/
ā āāā reservations.py # book/cancel + reservation resources + prompt
ā āāā availability.py # availability tool + resource
āāā scripts/
ā āāā walkthrough.py # manual interactive client
āāā var/ # runtime state, gitignored (holds bookings.json)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.